no code implementations • 31 Jan 2024 • Shreya Rajagopal, Subhashis Hazarika, Sookyung Kim, Yan-ming Chiou, Jae Ho Sohn, Hari Subramonyam, Shiwali Mohan
Given the recent advancements in Generative AI models aimed at improving the healthcare system, our work investigates whether and how generative visual question answering systems can responsibly support patient information needs in the context of radiology imaging data.
Computed Tomography (CT) Generative Visual Question Answering +2
no code implementations • 13 May 2023 • Subhashis Hazarika, Haruki Hirasawa, Sookyung Kim, Kalai Ramea, Salva R. Cachay, Peetak Mitra, Dipti Hingmire, Hansi Singh, Phil J. Rasch
Clouds have a significant impact on the Earth's climate system.
1 code implementation • 7 Feb 2023 • Soo Kyung Kim, Kalai Ramea, Salva Rühling Cachay, Haruki Hirasawa, Subhashis Hazarika, Dipti Hingmire, Peetak Mitra, Philip J. Rasch, Hansi A. Singh
Our model, AiBEDO, is capable of capturing the complex, multi-timescale effects of radiation perturbations on global and regional surface climate, allowing for a substantial acceleration of the exploration of the impacts of spatially-heterogenous climate forcers.
no code implementations • 3 Feb 2023 • Haruki Hirasawa, Sookyung Kim, Peetak Mitra, Subhashis Hazarika, Salva Ruhling-Cachay, Dipti Hingmire, Kalai Ramea, Hansi Singh, Philip J. Rasch
Here, we describe an AI model, named AiBEDO, that can be used to rapidly projects climate responses to forcings via a novel application of the Fluctuation-Dissipation Theorem (FDT).
no code implementations • 31 Aug 2020 • Subhashis Hazarika, Ayan Biswas, Phillip J. Wolfram, Earl Lawrence, Nathan Urban
With the increasing computational power of current supercomputers, the size of data produced by scientific simulations is rapidly growing.
no code implementations • 8 Dec 2019 • Qun Liu, Subhashis Hazarika, John M. Patchett, James Paul Ahrens, Ayan Biswas
Data modeling and reduction for in situ is important.
no code implementations • 19 Apr 2019 • Subhashis Hazarika, Haoyu Li, Ko-Chih Wang, Han-Wei Shen, Ching-Shan Chou
We utilize the trained network to perform interactive parameter sensitivity analysis of the original simulation at multiple levels-of-detail as well as recommend optimal parameter configurations using the activation maximization framework of neural networks.